ORKA v1.0.2

Release Notes

v1.0.2

ORKA v1.0.2 is a Zenodo-trigger patch release for orka-depth, published to
ensure the repository emits a fresh GitHub release event for DOI archival.

Repository:

• https://github.com/syedofc/orka-depth

Release highlights:

• bumps the public software version to 1.0.2
• preserves the DOI-ready citation and Zenodo metadata added in v1.0.1
• provides a fresh release snapshot for Zenodo ingestion

Practical scope:

• this is a release-trigger patch
• it does not change the software scope of ORKA
• it is the recommended release to use for Zenodo DOI minting

Quick start:

pip install "git+https://github.com/syedofc/orka-depth.git"
orka-validate

Verified release environment:

• Python 3.12.11
• torch 2.9.1+cu128
• torchvision 0.24.1+cu128

For fuller version guidance, see
https://github.com/syedofc/orka-depth/blob/main/docs/COMPATIBILITY.md

ORKA v1.0.1

Release Notes

v1.0.1

ORKA v1.0.1 is a metadata and citation update release for orka-depth,
prepared specifically to support cleaner archival and DOI minting workflows.

Repository:

• https://github.com/syedofc/orka-depth

Release highlights:

• improved CITATION.cff metadata with real author information
• added ORCID and affiliation for research attribution
• added .zenodo.json metadata for Zenodo software archiving
• aligned the software version metadata with the DOI-ready release tag

Included in this release:

• GitHub citation metadata for the repository landing page
• Zenodo-specific software metadata for release archiving
• updated version metadata for the public package

Practical scope:

• this is a metadata-focused patch release
• it keeps the same software scope as v1.0.0
• it is the recommended release to archive for DOI generation

Quick start:

pip install "git+https://github.com/syedofc/orka-depth.git"
orka-validate

Verified release environment:

• Python 3.12.11
• torch 2.9.1+cu128
• torchvision 0.24.1+cu128

For fuller version guidance, see
https://github.com/syedofc/orka-depth/blob/main/docs/COMPATIBILITY.md

ORKA v1.0.0

Release Notes

v1.0.0

ORKA v1.0.0 is the first public release of orka-depth, a lightweight PyTorch
toolkit for probing which intermediate feature depth of a frozen backbone works
best for a downstream task.

Repository:

• https://github.com/syedofc/orka-depth

Release highlights:

• reusable feature extraction helpers for common backbone layouts
• depth probing for classification and regression-style tasks
• CLI smoke tests for installation validation
• cleaned examples, docs, and compatibility guidance
• unit tests and CI-backed packaging

Included in this release:

• FeatureExtractor for pooled or raw intermediate activations
• find_optimal_depth for lightweight probe sweeps
• orka-validate and orka-find command-line entry points
• classification and pose-style synthetic examples
• documentation for install, compatibility, API usage, and roadmap

Practical scope:

• classification is the clearest out-of-the-box probe path
• pose and detection are treated as regression-style probe flows in this release
• the repository is positioned as a reusable toolkit, not a full paper
  reproduction package

Quick start:

pip install "git+https://github.com/syedofc/orka-depth.git"
orka-validate

Verified release environment:

• Python 3.12.11
• torch 2.9.1+cu128
• torchvision 0.24.1+cu128

For fuller version guidance, see
https://github.com/syedofc/orka-depth/blob/main/docs/COMPATIBILITY.md